Re: [PATCH v7 2/3] kho: fix deferred init of kho scratch

[Mike Rapoport <rppt@kernel.org>]

Hi Michal,

On Tue, Mar 17, 2026 at 03:15:33PM +0100, Michal Clapinski wrote:
> Currently, if DEFERRED is enabled, kho_release_scratch will initialize

Please spell out CONFIG_DEFERRED_STRUCT_PAGE_INIT

> the struct pages and set migratetype of kho scratch. Unless the whole
> scratch fit below first_deferred_pfn, some of that will be overwritten
> either by deferred_init_pages or memmap_init_reserved_pages.

Usually we put brackets after function names to make them more visible.
 
> To fix it, I modified kho_release_scratch to only set the migratetype

Prefer an imperative mood please, e.g. "To fix it, modify
kho_release_scratch() ..."

> on already initialized pages. Then, modified init_pageblock_migratetype
> to set the migratetype to CMA if the page is located inside scratch.
> 
> Signed-off-by: Michal Clapinski <mclapinski@google.com>
> ---
>  include/linux/memblock.h           |  2 --
>  kernel/liveupdate/kexec_handover.c | 10 ++++++----
>  mm/memblock.c                      | 22 ----------------------
>  mm/page_alloc.c                    |  7 +++++++
>  4 files changed, 13 insertions(+), 28 deletions(-)
> 
> diff --git a/include/linux/memblock.h b/include/linux/memblock.h
> index 6ec5e9ac0699..3e217414e12d 100644
> --- a/include/linux/memblock.h
> +++ b/include/linux/memblock.h
> @@ -614,11 +614,9 @@ static inline void memtest_report_meminfo(struct seq_file *m) { }
>  #ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
>  void memblock_set_kho_scratch_only(void);
>  void memblock_clear_kho_scratch_only(void);
> -void memmap_init_kho_scratch_pages(void);
>  #else
>  static inline void memblock_set_kho_scratch_only(void) { }
>  static inline void memblock_clear_kho_scratch_only(void) { }
> -static inline void memmap_init_kho_scratch_pages(void) {}
>  #endif
>  
>  #endif /* _LINUX_MEMBLOCK_H */
> diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c
> index c9b982372d6e..e511a50fab9c 100644
> --- a/kernel/liveupdate/kexec_handover.c
> +++ b/kernel/liveupdate/kexec_handover.c
> @@ -1477,8 +1477,7 @@ static void __init kho_release_scratch(void)
>  {
>  	phys_addr_t start, end;
>  	u64 i;
> -
> -	memmap_init_kho_scratch_pages();
> +	int nid;
>  
>  	/*
>  	 * Mark scratch mem as CMA before we return it. That way we
> @@ -1486,10 +1485,13 @@ static void __init kho_release_scratch(void)
>  	 * we can reuse it as scratch memory again later.
>  	 */
>  	__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
> -			     MEMBLOCK_KHO_SCRATCH, &start, &end, NULL) {
> +			     MEMBLOCK_KHO_SCRATCH, &start, &end, &nid) {
>  		ulong start_pfn = pageblock_start_pfn(PFN_DOWN(start));
>  		ulong end_pfn = pageblock_align(PFN_UP(end));
>  		ulong pfn;
> +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
> +		end_pfn = min(end_pfn, NODE_DATA(nid)->first_deferred_pfn);
> +#endif

A helper that returns first_deferred_pfn or ULONG_MAX might be beeter
looking. 

>  
>  		for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages)
>  			init_pageblock_migratetype(pfn_to_page(pfn),
> @@ -1500,8 +1502,8 @@ static void __init kho_release_scratch(void)
>  void __init kho_memory_init(void)
>  {
>  	if (kho_in.scratch_phys) {
> -		kho_scratch = phys_to_virt(kho_in.scratch_phys);
>  		kho_release_scratch();
> +		kho_scratch = phys_to_virt(kho_in.scratch_phys);

Why this change is needed?

>  
>  		if (kho_mem_retrieve(kho_get_fdt()))
>  			kho_in.fdt_phys = 0;
> diff --git a/mm/memblock.c b/mm/memblock.c
> index b3ddfdec7a80..ae6a5af46bd7 100644
> --- a/mm/memblock.c
> +++ b/mm/memblock.c
> @@ -959,28 +959,6 @@ __init void memblock_clear_kho_scratch_only(void)
>  {
>  	kho_scratch_only = false;
>  }
> -
> -__init void memmap_init_kho_scratch_pages(void)
> -{
> -	phys_addr_t start, end;
> -	unsigned long pfn;
> -	int nid;
> -	u64 i;
> -
> -	if (!IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT))
> -		return;
> -
> -	/*
> -	 * Initialize struct pages for free scratch memory.
> -	 * The struct pages for reserved scratch memory will be set up in
> -	 * reserve_bootmem_region()
> -	 */
> -	__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
> -			     MEMBLOCK_KHO_SCRATCH, &start, &end, &nid) {
> -		for (pfn = PFN_UP(start); pfn < PFN_DOWN(end); pfn++)
> -			init_deferred_page(pfn, nid);
> -	}
> -}
>  #endif
>  
>  /**
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index ee81f5c67c18..5ca078dde61d 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -55,6 +55,7 @@
>  #include <linux/cacheinfo.h>
>  #include <linux/pgalloc_tag.h>
>  #include <linux/mmzone_lock.h>
> +#include <linux/kexec_handover.h>
>  #include <asm/div64.h>
>  #include "internal.h"
>  #include "shuffle.h"
> @@ -549,6 +550,12 @@ void __meminit init_pageblock_migratetype(struct page *page,
>  		     migratetype < MIGRATE_PCPTYPES))
>  		migratetype = MIGRATE_UNMOVABLE;
>  
> +	/*
> +	 * Mark KHO scratch as CMA so no unmovable allocations are made there.
> +	 */
> +	if (unlikely(kho_scratch_overlap(page_to_phys(page), PAGE_SIZE)))
> +		migratetype = MIGRATE_CMA;
> +

Please pick SJ's fixup for the next respin :)

>  	flags = migratetype;
>  
>  #ifdef CONFIG_MEMORY_ISOLATION
> -- 
> 2.53.0.851.ga537e3e6e9-goog
> 

-- 
Sincerely yours,
Mike.